Topics within our research lines for B. Sc. thesis (TFG) and M. Sc. thesis (TFM):

OBJETIVE:

This thesis aims to conduct a comprehensive comparison between two prominent deep reinforcement learning algorithms, Asynchronous Advantage Actor-Critic (A3C) and Soft Actor-Critic (SAC). Both A3C and SAC have demonstrated remarkable success in tackling complex tasks in continuous and discrete action spaces, respectively. However, a thorough investigation into their strengths, weaknesses, and performance across various benchmarks and environments remains unexplored.

This study will compare both algorithms in Python using TensorFlow and OpenAI Gym (A3C provided), providing an in-depth analysis of their sample efficiency, convergence rate, stability, and scalability.

REQUIREMENTS:

Python (TensorFlow), Reinforcement Learning theory

CONTACT PERSON:

Alberto del Río – arp@gatv.ssr.upm.es

OBJETIVE:

The proposed Master thesis aims to develop a media production control module for optimizing content creation processes. The Studio Production module will integrate information from diverse sources and employ innovative techniques to produce media content that seamlessly combines these inputs into a cohesive and engaging stream.

REQUIREMENTS:

Python, Multimedia tools (OBS).

CONTACT PERSON:

Álvaro Llorente – alg@gatv.ssr.upm.es

OBJECTIVE:

The objective of this Bachelor/Master thesis is to conduct a comprehensive comparison between different network measurement tools to evaluate their capabilities in assessing various network characteristics, such as jitter, bandwidth, latency, and packet loss. The study will focus on open-source tools, including Scapy for Python, Socket programming, ping, nmap, and pyping, to understand their included features and the time taken to perform these measurements accurately.

REQUIREMENTS:

Network fundamentals (TCP/UDP); Programming languages (Bash, Python)

CONTACT PERSON:

Alberto del Río – arp@gatv.ssr.upm.es

OBJECTIVE:

The objective of this Master’s thesis is to design and implement algorithms for network anomaly detection. The study aims to develop a system that can identify unusual behavior, security threats, and potential network outages by analyzing network traffic patterns. By utilizing machine learning techniques, the research will focus on creating an efficient and accurate anomaly detection system for network administrators and security personnel.

REQUIREMENTS:

Network fundamentals (TCP/UDP); Programming languages (Bash, Python)

CONTACT PERSON:

Alberto del Río – arp@gatv.ssr.upm.es

OBJECTIVE:

The goal of this Master’s thesis is to develop a predictive model for bandwidth usage based on historical data. The study will analyze and process historical bandwidth usage patterns to forecast future bandwidth demands accurately. By employing time series analysis, machine learning, or statistical methods, the research aims to provide network administrators with valuable insights to proactively manage network resources, prevent congestion, and optimize overall network performance.

REQUIREMENTS:

Network fundamentals (TCP/UDP); Programming languages (Bash, Python)

CONTACT PERSON:

Javier Serrano – jsr@gatv.ssr.upm.es

OBJECTIVE:

The objective of this Master’s thesis is to optimize dynamic routing algorithms for faster and more efficient packet delivery in computer networks. The research will focus on analyzing routing paths, network topology, and link conditions to propose enhancements to existing dynamic routing protocols. The study aims to improve the routing decision-making process, reduce latency, and optimize the network’s ability to adapt to changing conditions.

REQUIREMENTS:

Network fundamentals (TCP/UDP); Programming languages (Bash, Python)

CONTACT PERSON:

Javier Serrano – jsr@gatv.ssr.upm.es

OBJECTIVE:

The goal of this Master’s thesis is to develop a comprehensive network health scoring system that evaluates multiple performance metrics to provide an overall network health assessment. The research will identify key network performance indicators, such as bandwidth utilization, latency, packet loss, and error rates, and develop a scoring system to quantify the network’s overall health. By leveraging data analysis and visualization techniques, the study aims to empower network administrators with a holistic view of the network’s performance, aiding in proactive maintenance and troubleshooting efforts.

REQUIREMENTS:

Network fundamentals (TCP/UDP); Programming languages (Bash, Python)

CONTACT PERSON:

Alberto del Río– arp@gatv.ssr.upm.es

OBJECTIVE:

Network performance is critical for ensuring efficient and reliable data transmission in modern communication infrastructures. This proposal outlines the development of a versatile and comprehensive network performance probe using Python. The proposed probe will leverage various online measurement tools to assess critical network characteristics, including latency, jitter, bandwidth, and packet loss.

REQUIREMENTS:

Network fundamentals (TCP/UDP); Programming languages (Bash, Python)

CONTACT PERSON:

Alberto del Río– arp@gatv.ssr.upm.es